CN112634170A - Blurred image correction method and device, computer equipment and storage medium - Google Patents
Blurred image correction method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN112634170A CN112634170A CN202011609062.4A CN202011609062A CN112634170A CN 112634170 A CN112634170 A CN 112634170A CN 202011609062 A CN202011609062 A CN 202011609062A CN 112634170 A CN112634170 A CN 112634170A
- Authority
- CN
- China
- Prior art keywords
- image
- frame
- restored
- repaired
- target video
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 80
- 238000003702 image correction Methods 0.000 title claims description 24
- 239000011159 matrix material Substances 0.000 claims description 173
- 230000004927 fusion Effects 0.000 claims description 76
- 238000005457 optimization Methods 0.000 claims description 58
- 230000006870 function Effects 0.000 claims description 55
- 238000001514 detection method Methods 0.000 claims description 43
- 230000007547 defect Effects 0.000 claims description 37
- 238000012545 processing Methods 0.000 claims description 19
- 238000010606 normalization Methods 0.000 claims description 12
- 238000013473 artificial intelligence Methods 0.000 abstract description 9
- 238000004364 calculation method Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 3
- 238000002940 Newton-Raphson method Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 230000004069 differentiation Effects 0.000 description 2
- 230000002349 favourable effect Effects 0.000 description 2
- 230000000306 recurrent effect Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/73—Deblurring; Sharpening
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/77—Retouching; Inpainting; Scratch removal
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The application discloses a method and a device for correcting a blurred image, computer equipment and a storage medium, and belongs to the technical field of artificial intelligence. The present application also relates to blockchain techniques in which target video may be stored. The technical scheme of the application can correct the image blur caused by high-speed movement or low-speed movement of the object, has high adaptability, does not increase the occupation of system resources, and is suitable for being deployed on the mobile terminal.
Description
Technical Field
The application belongs to the technical field of artificial intelligence, and particularly relates to a method and a device for correcting a blurred image, computer equipment and a storage medium.
Background
With the wide use of artificial intelligence in the financial field, scenes for developing financial behaviors at a mobile terminal are more and more abundant, and the scenes involve strict approval services, such as face recognition approval services. And a client image is required to be acquired for verification in the face recognition approval service. In consideration of experience, a client image for face recognition is often a picture obtained by extracting a corresponding picture frame from a video shot by a camera at a mobile terminal of a user, but the quality of the picture obtained in this way is often not guaranteed, and especially, the slight movement of the mobile terminal can cause the blurring of the image, and such image defects are extremely disadvantageous for tasks such as face recognition.
Therefore, in order to effectively improve the accuracy of face recognition, it is imperative to optimize the image quality. For image blur restoration caused by rapid movement of a camera relative to a photographed object, some methods based on a kalman filter are generally adopted, and such methods have certain limitations, for example, the image restoration method based on the kalman filter is insufficient in generalization capability, and restoration cannot be realized for an image moving at a high speed, so a scheme designed by simply adopting the kalman filter method often does not have high adaptability, and other restoration methods need to be additionally added to realize high-speed moving image restoration, but the occupation of system resources is undoubtedly increased, and the method is not favorable for being deployed in a mobile terminal. In addition, although the deep learning convolutional neural network method which is raised in recent years has good adaptability, the calculation cost is large, and the deep learning convolutional neural network method is not favorable for being embedded into a mobile terminal.
Disclosure of Invention
An embodiment of the application aims to provide a method, a device, computer equipment and a storage medium for correcting a blurred image, so as to solve the technical problems that the existing image blur restoration scheme is insufficient in generalization capability, high in calculation cost and not beneficial to being embedded into a mobile terminal.
In order to solve the above technical problem, an embodiment of the present application provides a method for correcting a blurred image, which adopts the following technical solutions:
a method of blurred image correction, comprising:
receiving an image restoration instruction, acquiring a target video corresponding to the image restoration instruction, and acquiring all image frames in the target video;
determining an image to be restored in all image frames of a target video based on a preset image detection strategy;
importing the detected image to be restored into a pre-trained image deformation prediction model to obtain a deformation matrix of the image to be restored;
constructing a deformation matrix optimization function, and performing iterative update on the deformation matrix based on the deformation matrix optimization function to obtain an image fusion weight matrix;
and performing image fusion on the image to be restored and the previous frame image of the image to be restored based on the image fusion weight matrix to obtain a restored image, and replacing the image to be restored by the restored image.
Further, after the steps of receiving an image restoration instruction, acquiring a target video corresponding to the image restoration instruction, and acquiring all image frames in the target video, the method further comprises:
carrying out graying processing on all image frames respectively to obtain a grayscale image of each image frame;
and carrying out normalization processing on the gray level image of each image frame to obtain a normalized image matrix corresponding to each image frame.
Further, before the step of determining an image to be restored in all image frames of the target video based on a preset image detection strategy, the method further includes:
detecting a first image frame of the target video based on a preset standard image index, and judging whether the first image frame is a standard image frame;
and if the first image frame is not the standard image frame, re-intercepting the target video corresponding to the image restoration instruction.
Further, the step of determining an image to be restored in all image frames of the target video based on a preset image detection strategy specifically includes:
acquiring two image frames connected in time sequence from a target video, wherein the two image frames connected in time sequence are a current image frame and a previous image frame at a previous moment of the current image frame;
and leading the current image frame and the previous image frame into a preset defect detector to obtain an image defect detection result, and determining whether the current image frame is an image to be repaired based on the image defect detection result.
Further, the method comprises the steps of importing a current image frame and a previous image frame into a preset defect detector to obtain an image defect detection result, and determining whether the current image frame is an image to be repaired based on the image defect detection result, wherein the steps specifically comprise:
calculating the similarity between the current image frame and the previous image frame to obtain a first similarity;
comparing the first similarity with a preset similarity threshold;
and if the first similarity is smaller than a preset similarity threshold, determining that the current image frame is an image to be restored.
Further, the step of constructing a deformation matrix optimization function, and iteratively updating the deformation matrix based on the deformation matrix optimization function to obtain an image fusion weight matrix specifically includes:
carrying out normalization processing on the deformation matrix to obtain an initial fusion weight matrix;
calculating a weight factor of the image to be restored, and constructing a deformation matrix optimization function based on the weight factor;
iterating the deformation matrix optimization function based on a Newton method;
and optimizing the initial fusion weight matrix through the iterated deformation matrix optimization function to obtain a fusion weight matrix.
Further, after the image fusion is performed on the image to be restored and the previous frame image of the image to be restored based on the image fusion weight matrix to obtain a restored image, and the image to be restored is replaced by the restored image, the method further includes:
leading the obtained repaired image frame and the previous image frame into a preset defect detector, and calculating the similarity between the repaired image frame and the previous image frame to obtain a second similarity;
comparing the second similarity with a preset similarity threshold;
and if the second similarity is smaller than the preset similarity threshold, continuously repairing the image of the repaired image frame until the second similarity is larger than or equal to the preset similarity threshold.
In order to solve the above technical problem, an embodiment of the present application further provides a device for correcting a blurred image, which adopts the following technical solutions:
an apparatus for blurred image correction, comprising:
the target video acquisition module is used for receiving the image restoration instruction, acquiring a target video corresponding to the image restoration instruction and acquiring all image frames in the target video;
the device comprises a to-be-repaired image determining module, a to-be-repaired image determining module and a to-be-repaired image determining module, wherein the to-be-repaired image determining module is used for determining an image to be repaired in all image frames of a target video based on a preset image detection strategy;
the deformation matrix obtaining module is used for leading the detected image to be repaired into a pre-trained image deformation prediction model to obtain a deformation matrix of the image to be repaired;
the deformation matrix optimization module is used for constructing a deformation matrix optimization function and iteratively updating the deformation matrix based on the deformation matrix optimization function to obtain an image fusion weight matrix;
and the image restoration module is used for carrying out image fusion on the image to be restored and the image of the previous frame of the image to be restored based on the image fusion weight matrix to obtain a restored image and replacing the image to be restored by the restored image.
In order to solve the above technical problem, an embodiment of the present application further provides a computer device, which adopts the following technical solutions:
a computer device comprising a memory having computer readable instructions stored therein and a processor which when executed implements the steps of the method of blurred image correction according to any of the above.
In order to solve the above technical problem, an embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solutions:
a computer readable storage medium having computer readable instructions stored thereon which, when executed by a processor, implement the steps of the method of blurred image correction as described above.
Compared with the prior art, the embodiment of the application mainly has the following beneficial effects:
the application discloses a method and a device for correcting a blurred image, computer equipment and a storage medium, and belongs to the technical field of artificial intelligence. Because the image frames in the target video are often continuous, although the quality of the extracted target image frame is not excellent, the information contained in the fuzzy part of the target image is deduced from the image at the moment of the target image frame, and the information is fused with the target image, so that the information of the image can be recovered, and the aim of image restoration is fulfilled. According to the method, the image to be restored is determined in all image frames of the target video through a preset image detection strategy, the image to be restored is led into a pre-trained image deformation prediction model to obtain a deformation matrix of the image to be restored, a deformation matrix optimization function is constructed, the deformation matrix is subjected to iterative updating based on the deformation matrix optimization function to obtain an image fusion weight matrix, the image to be restored and the image of the previous frame of the image to be restored are subjected to image fusion based on the image fusion weight matrix to obtain a restored image, and the restored image is replaced by the obtained restored image. The technical scheme of the application can correct the image blur caused by high-speed movement or low-speed movement of the object, has high adaptability, does not increase the occupation of system resources, does not increase the overhead of the system, and is suitable for being deployed at the mobile terminal.
Drawings
In order to more clearly illustrate the solution of the present application, the drawings needed for describing the embodiments of the present application will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present application, and that other drawings can be obtained by those skilled in the art without inventive effort.
FIG. 1 illustrates an exemplary system architecture diagram in which the present application may be applied;
FIG. 2 illustrates a flow diagram of one embodiment of a method of blurred image correction according to the present application;
FIG. 3 shows a schematic structural diagram of an embodiment of an apparatus for blurred image correction according to the present application;
FIG. 4 shows a schematic block diagram of one embodiment of a computer device according to the present application.
Detailed Description
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used in the description of the application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "including" and "having," and any variations thereof, in the description and claims of this application and the description of the above figures are intended to cover non-exclusive inclusions. The terms "first," "second," and the like in the description and claims of this application or in the above-described drawings are used for distinguishing between different objects and not for describing a particular order.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.
As shown in fig. 1, the system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the terminal devices 101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The user may use the terminal devices 101, 102, 103 to interact with the server 105 via the network 104 to receive or send messages or the like. The terminal devices 101, 102, 103 may have various communication client applications installed thereon, such as a web browser application, a shopping application, a search application, an instant messaging tool, a mailbox client, social platform software, and the like.
The terminal devices 101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture experts Group Audio Layer III, mpeg compression standard Audio Layer 3), MP4 players (Moving Picture experts Group Audio Layer IV, mpeg compression standard Audio Layer 4), laptop portable computers, desktop computers, and the like.
The server 105 may be a server providing various services, such as a background server providing support for pages displayed on the terminal devices 101, 102, 103.
It should be noted that the method for correcting the blurred image provided by the embodiment of the present application is generally executed by a terminal device, and accordingly, the apparatus for correcting the blurred image is generally disposed in the terminal device.
It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
With continued reference to FIG. 2, a flow diagram of one embodiment of a method of blurred image correction according to the present application is shown. The method for correcting the blurred image comprises the following steps:
s201, receiving an image restoration instruction, acquiring a target video corresponding to the image restoration instruction, and acquiring all image frames in the target video.
Specifically, when an image needs to be repaired, an image repairing instruction input by a user from a user terminal is received, and a target video corresponding to the image repairing instruction is acquired. The user terminal can be a mobile terminal, such as a smart phone, and the target video can be a video which is shot by the user and exists in a mobile terminal database, or a video which is shot by the user through a camera of the mobile terminal.
In this embodiment, the electronic device (for example, the server/terminal device shown in fig. 1) on which the method for correcting the blurred image operates may receive the image restoration instruction by a wired connection manner or a wireless connection manner. It should be noted that the wireless connection means may include, but is not limited to, a 3G/4G connection, a WiFi connection, a bluetooth connection, a WiMAX connection, a Zigbee connection, a uwb (ultra wideband) connection, and other wireless connection means now known or developed in the future.
S202, determining an image to be restored in all image frames of the target video based on a preset image detection strategy.
Specifically, the image restoration instruction includes a preset image detection strategy, after the image restoration instruction is received, the preset image detection strategy corresponding to the image restoration instruction is extracted, and the image to be restored is determined in all the image frames in the target video in sequence through the preset image detection strategy. The preset image detection strategy may be to determine whether the current image frame is an image to be restored by comparing two image frames connected in time sequence, where the two image frames connected in time sequence are the current image frame and a previous image frame at a previous time of the current image frame. Because the image frames in the target video are often continuous, although the quality of the extracted target image frame is not excellent, the information contained in the fuzzy part of the target image is deduced from the image at the moment of the target image frame, and the information is fused with the target image, so that the information of the image can be recovered, and the aim of image restoration is fulfilled.
S203, importing the detected image to be restored into a pre-trained image deformation prediction model to obtain a deformation matrix of the image to be restored.
The image deformation prediction model can be constructed in advance based on the RNN recurrent neural network, and in the image deformation prediction model constructed in advance, a matrix how the image is degraded, namely a deformation matrix of the input image sequence, can be obtained according to the input image sequence. In a specific embodiment of the present application, an RNN recurrent neural network is used for image deformation prediction, an input parameter of an image deformation prediction model is an image sequence I _ r to be repaired, the image sequence I _ r to be repaired at least includes a current image frame and a previous image frame, and a target portion of a deformation matrix output by the prediction model is obtained by the following method: and after the two graphs with the time sequence order are converted into gray graphs, the gray difference value can be obtained by directly making difference, and the gray difference value is filled into the target part of the initial deformation matrix to form the deformation matrix. In the process of training the deformation prediction model, a training sample can be a pre-collected image sequence needing image restoration, the image sequence is labeled and then is imported into an initial image deformation prediction model, a loss function corresponding to the initial image deformation prediction model is constructed, the initial image deformation prediction model is iterated based on a prediction result and the constructed loss function until the model is fitted, and the trained image deformation prediction model is output.
Specifically, a matrix difference between the image to be restored and a previous image frame is calculated, and the matrix difference is a deformation matrix of the image to be restored. After two graphs with time sequence order are converted into gray level graphs, the gray level difference value of each element position on the image matrix can be obtained by directly making difference, and the gray level difference value of each element position is filled into the target part of the corresponding position of the deformation matrix, so that the deformation matrix of the image to be repaired is obtained.
S204, a deformation matrix optimization function is constructed, and the deformation matrix is iteratively updated based on the deformation matrix optimization function to obtain an image fusion weight matrix.
Specifically, a weight factor of the image to be restored is calculated, wherein the weight factor of the image to be restored represents a deformation degree of the image to be restored, an initial image fusion weight matrix can be obtained by normalizing the deformation matrix, and the calculation is performed through specific parameters in the initial image fusion weight matrix. And constructing the deformation matrix optimization function based on the weight factors, iterating the deformation matrix optimization function based on a Newton method, and iterating and updating the initial image fusion weight matrix through the iterated deformation matrix optimization function to obtain a fusion weight matrix.
S205, image fusion is carried out on the image to be repaired and the image of the previous frame of the image to be repaired based on the image fusion weight matrix to obtain a repaired image, and the image to be repaired is replaced by the repaired image.
Specifically, after the fusion weight matrix is obtained, the image to be restored and the previous frame image of the image to be restored are fused based on the fusion weight matrix obtained through calculation and an alpha image fusion algorithm, so that the restored image is obtained. For example, an image to be restored is M, a previous image of a time sequence of the image to be restored is N, a value of a p element on an M matrix of the image to be restored is I, a value of an element at a position corresponding to the p element on the N matrix of the previous image of the time sequence of the image to be restored is I, a weight value of the p element in a fusion weight matrix is v, the M and N are fused according to the following fusion proportion (1-v) × I + v |, based on the fusion weight matrix obtained by calculation and an alpha image fusion algorithm, so as to obtain a restored image M ', and the restored image M' obtained after fusion is substituted for the original M. In a specific embodiment of the present application, the image quality of the repaired image M 'is continuously detected, and if the image quality of the repaired image M' does not meet the requirement, the image repairing process is repeated until the finally obtained image quality of the image M meets the requirement.
The application discloses a method for correcting a blurred image, and belongs to the technical field of artificial intelligence. Because the image frames in the target video are often continuous, although the quality of the extracted target image frame is not excellent, the information contained in the fuzzy part of the target image is deduced from the image at the moment of the target image frame, and the information is fused with the target image, so that the information of the image can be recovered, and the aim of image restoration is fulfilled. According to the method, the image to be restored is determined in all image frames of the target video through a preset image detection strategy, the image to be restored is led into a pre-trained image deformation prediction model to obtain a deformation matrix of the image to be restored, a deformation matrix optimization function is constructed, the deformation matrix is subjected to iterative updating based on the deformation matrix optimization function to obtain an image fusion weight matrix, the image to be restored and the image of the previous frame of the image to be restored are subjected to image fusion based on the image fusion weight matrix to obtain a restored image, and the restored image is replaced by the obtained restored image. The technical scheme of the application can correct the image blur caused by high-speed movement or low-speed movement of the object, has high adaptability, does not increase the occupation of system resources, does not increase the overhead of the system, and is suitable for being deployed at the mobile terminal.
Further, after the steps of receiving an image restoration instruction, acquiring a target video corresponding to the image restoration instruction, and acquiring all image frames in the target video, the method further comprises:
carrying out graying processing on all image frames respectively to obtain a grayscale image of each image frame;
and carrying out normalization processing on the gray level image of each image frame to obtain a normalized image matrix corresponding to each image frame.
Specifically, graying is to make each pixel point in the image satisfy the following relationship: r, G, B, X, wherein R, G, B is the tristimulus channel, where X is called the gray scale value, and X is a specific value between 0 and 255. The method comprises the steps of performing graying processing on all image frames to obtain a grayscale image of each image frame, wherein each pixel point of the grayscale image is represented by a grayscale value, the grayscale image can be regarded as a matrix, and the value range of elements in the grayscale image matrix is between 0 and 255. And carrying out normalization processing on each pixel point in the gray level image matrix to obtain a normalized image matrix corresponding to the gray level image, so that the value of the pixel value of each pixel point is between 0 and 1.
Further, before the step of determining an image to be restored in all image frames of the target video based on a preset image detection strategy, the method further includes:
detecting a first image frame of the target video based on a preset standard image index, and judging whether the first image frame is a standard image frame;
and if the first image frame is not the standard image frame, re-intercepting the target video corresponding to the image restoration instruction.
Specifically, a judgment condition for judging a standard image frame is preset in the image restoration instruction, a first image frame of the target video is detected based on the judgment condition, whether the first image frame is the standard image frame or not is judged, and if the first image frame is the standard image frame, the step of determining the image to be restored in all the image frames of the target video is continuously executed. And if the first image frame is not the standard image frame, outputting prompt information that the first image frame does not meet the requirements, and re-intercepting the target video corresponding to the image restoration instruction to obtain a new target video.
Further, the step of determining an image to be restored in all image frames of the target video based on a preset image detection strategy specifically includes:
acquiring two image frames connected in time sequence from a target video, wherein the two image frames connected in time sequence are a current image frame and a previous image frame at a previous moment of the current image frame;
and leading the current image frame and the previous image frame into a preset defect detector to obtain an image defect detection result, and determining whether the current image frame is an image to be repaired based on the image defect detection result.
The method comprises the following steps of detecting all image frames in a target video by using a preset defect detector, wherein the detection thought of the defect detector is described as follows: in a section of normal continuous video image frame, the image contents of the front frame and the back frame should be basically unchanged, so the image quality discriminator based on the contents is adopted to calculate the similarity of the front frame and the back frame, namely when the front frame is used as a reference image and the back frame is used as an image to be evaluated, the image content difference between the front frame and the back frame is smaller, so the requirement on the image quality evaluation of the back frame should be higher, and once the image content changes due to rapid movement and the like, namely when the image to be evaluated is equivalent to larger degradation on the basis of the reference image, the difference between the image of the back frame and the image of the front frame is enlarged, and a defect detector is constructed on the basis of the difference. Therefore, by designing a similarity threshold, when the similarity between the next frame image and the previous frame image is higher than the similarity threshold, the image to be repaired is considered not to be required to be corrected, otherwise, the image to be repaired is considered to be required to be corrected.
Specifically, a current image frame and a previous image frame are led into a preset defect detector, the previous image frame is used as a standard image frame which does not need to be repaired, the similarity between the current image frame and the previous image frame is calculated, and whether the current image frame is an image to be repaired is determined by comparing the similarity with a preset similarity threshold value. In a specific embodiment of the present application, image quality detection is performed on all image frames in the target video in a traversal manner starting from the first image frame of the target video, and therefore the first image frame of the target video must be a standard image frame meeting the requirement of the quality condition. In the image quality detection process, when a defect detector detects each image to be repaired, the image to be repaired is repaired firstly until the image to be repaired is repaired, and then the defect detector continues to detect the subsequent image frames until all the image frames in the target video finish the image quality detection.
Further, the method comprises the steps of importing a current image frame and a previous image frame into a preset defect detector to obtain an image defect detection result, and determining whether the current image frame is an image to be repaired based on the image defect detection result, wherein the steps specifically comprise:
calculating the similarity between the current image frame and the previous image frame to obtain a first similarity;
comparing the first similarity with a preset similarity threshold;
and if the first similarity is smaller than a preset similarity threshold, determining that the current image frame is an image to be restored.
Specifically, the similarity between the current image frame and the previous image frame is calculated by comparing pixel values of each pixel point corresponding to each other on the current image frame and the previous image frame to obtain a first similarity, whether the current image frame is an image to be restored is determined by comparing the first similarity with a preset similarity threshold, if the first similarity is smaller than the preset similarity threshold, the current image frame is determined to be the image to be restored, and if the first similarity is larger than or equal to the preset similarity threshold, the current image frame is determined to be the image which does not need to be restored.
Further, the step of constructing a deformation matrix optimization function, and iteratively updating the deformation matrix based on the deformation matrix optimization function to obtain an image fusion weight matrix specifically includes:
carrying out normalization processing on the deformation matrix to obtain an initial fusion weight matrix;
calculating a weight factor of the image to be restored, and constructing a deformation matrix optimization function based on the weight factor;
iterating the deformation matrix optimization function based on a Newton method;
and optimizing the initial fusion weight matrix through the iterated deformation matrix optimization function to obtain a fusion weight matrix.
It should be noted that Newton's method is also called Newton-Raphson method, and Newton-Raphson method is an iterative solution method, and an optimization problem can be solved by using Newton method, where the optimization problem is a solution of a certain problem with countless possible results, and solving the optimization problem is a result that finds the best condition among countless possible results.
Specifically, after the deformation matrix is obtained, the deformation matrix is normalized to obtain an initial fusion weight matrix, and a weight factor of the image to be restored is calculated based on the initial fusion weight matrix, where the weight factor of the image to be restored includes a weight factor in the x direction and a weight factor in the y direction, and is specifically represented as follows:
wherein, ω isx,pIs in the x directionWeight factor of, ωy,pIs a weight factor in the y direction, p is a specific element of the initial fusion weight matrix, L'pRefers to the value of the element at the p-point,means partial differentiation in the x-direction of the initial fusion weight matrix,means that partial differentiation is carried out on the y direction of the initial fusion weight matrix, epsilon is a constant, Tx,p、Ty,pIs RTV (relative total variation) operator, which is specifically expressed as follows:
wherein Ω refers to an image block patch, in the present application, the size of the image block patch is 15x15, q refers to another specific element on the initial fusion weight matrix, p and q are both in the image block patch, Gσ(p, q) is a Gaussian function, which is expressed as follows:
wherein G isσ(p, q) is an e-index function, D (p, q) is a straight-line distance between two points p and q, and sigma is the overall variance of the image block patch, and the design is designed for the purpose of preventing distortion in calculation, so that the smoothing processing based on Gaussian weighting is designed.
So far, all the parameters of the deformation matrix optimization function are constructed, and the specific deformation matrix optimization function is expressed as follows:
wherein λ is a constant parameter, LpIs the matrix value of the element corresponding to the above-mentioned p element in the matrix of the image to be restored. In the specific embodiment of the present application, after the deformation matrix optimization function is constructed, a method needs to be used to find the weight matrix meeting such conditions, and the deformation matrix optimization function can be solved by using a newton method according to the form of the optimization function to obtain the fusion weight matrix.
Further, after the image fusion is performed on the image to be restored and the previous frame image of the image to be restored based on the image fusion weight matrix to obtain a restored image, and the image to be restored is replaced by the restored image, the method further includes:
leading the obtained repaired image frame and the previous image frame into a preset defect detector, and calculating the similarity between the repaired image frame and the previous image frame to obtain a second similarity;
comparing the second similarity with a preset similarity threshold;
and if the second similarity is smaller than the preset similarity threshold, continuously repairing the image of the repaired image frame until the second similarity is larger than or equal to the preset similarity threshold.
Specifically, after the image to be restored is replaced by the restored image, the obtained restored image frame and the previous image frame are led into a preset defect detector, the similarity between the restored image frame and the previous image frame is calculated to obtain a second similarity, the second similarity is compared with a preset similarity threshold, if the second similarity is larger than or equal to the preset similarity threshold, the restoration of the current image frame is stopped, and the next image to be restored is checked. And if the second similarity is smaller than the preset similarity threshold, continuously repairing the image of the repaired image frame until the second similarity is larger than or equal to the preset similarity threshold.
At present, scenes for developing financial behaviors at a mobile terminal are more and more abundant, and the scenes all involve stricter approval services, such as face recognition approval services. In the face recognition process, a client image needs to be acquired for verification, and in consideration of experience, the client image used for face recognition is often a picture obtained by extracting a corresponding picture frame from a video shot by a camera at a mobile terminal of a user, but the quality of the picture obtained in the manner cannot be guaranteed, especially, the image is blurred due to slight movement of the mobile terminal, and such image defects are extremely disadvantageous for tasks such as face recognition.
In order to solve the technical problems, the application discloses a method for correcting a blurred image, and belongs to the technical field of artificial intelligence. Because the image frames in the target video are often continuous, although the quality of the extracted target image frame is not excellent, the information contained in the fuzzy part of the target image is deduced from the image at the moment of the target image frame, and the information is fused with the target image, so that the information of the image can be recovered, and the aim of image restoration is fulfilled. According to the method, the image to be restored is determined in all image frames of the target video through a preset image detection strategy, the image to be restored is led into a pre-trained image deformation prediction model to obtain a deformation matrix of the image to be restored, a deformation matrix optimization function is constructed, the deformation matrix is subjected to iterative updating based on the deformation matrix optimization function to obtain an image fusion weight matrix, the image to be restored and the image of the previous frame of the image to be restored are subjected to image fusion based on the image fusion weight matrix to obtain a restored image, and the restored image is replaced by the obtained restored image. The technical scheme of the application can correct the image blur caused by high-speed movement or low-speed movement of the object, has high adaptability, does not increase the occupation of system resources, does not increase the overhead of the system, and is suitable for being deployed at the mobile terminal.
It is emphasized that, to further ensure the privacy and security of the target video, the target video may also be stored in a node of a blockchain.
The block chain referred by the application is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware associated with computer readable instructions, which can be stored in a computer readable storage medium, and when executed, can include processes of the embodiments of the methods described above. The storage medium may be a non-volatile storage medium such as a magnetic disk, an optical disk, a Read-Only Memory (ROM), or a Random Access Memory (RAM).
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and may be performed in other orders unless explicitly stated herein. Moreover, at least a portion of the steps in the flow chart of the figure may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed alternately or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
With further reference to fig. 3, as an implementation of the method shown in fig. 2, the present application provides an embodiment of an apparatus for blur image correction, which corresponds to the embodiment of the method shown in fig. 2, and which is particularly applicable to various electronic devices.
As shown in fig. 3, the blurred image correction apparatus according to the present embodiment includes:
a target video obtaining module 301, configured to receive an image restoration instruction, obtain a target video corresponding to the image restoration instruction, and obtain all image frames in the target video;
a to-be-repaired image determining module 302, configured to determine an image to be repaired in all image frames of a target video based on a preset image detection policy;
a deformation matrix obtaining module 303, configured to import the detected image to be repaired into a pre-trained image deformation prediction model, so as to obtain a deformation matrix of the image to be repaired;
the deformation matrix optimization module 304 is configured to construct a deformation matrix optimization function, and iteratively update the deformation matrix based on the deformation matrix optimization function to obtain an image fusion weight matrix;
the image restoration module 305 is configured to perform image fusion on the image to be restored and the previous frame image of the image to be restored based on the image fusion weight matrix to obtain a restored image, and replace the image to be restored with the restored image.
Further, the apparatus for blurred image correction further includes:
the graying processing module is used for respectively carrying out graying processing on all the image frames to obtain a grayscale image of each image frame;
and the normalization processing module is used for performing normalization processing on the gray level image of each image frame to obtain a normalization image matrix corresponding to each image frame.
Further, the apparatus for blurred image correction further includes:
the standard image frame detection module is used for detecting a first image frame of the target video based on a preset standard image index and judging whether the first image frame is the standard image frame;
and the standard image frame detection result module is used for re-intercepting the target video corresponding to the image restoration instruction when the first image frame is not the standard image frame.
Further, the to-be-repaired image determining module 302 specifically includes:
the image frame acquisition unit is used for acquiring two image frames connected in time sequence from the target video, wherein the two image frames connected in time sequence are a current image frame and a previous image frame at a previous moment of the current image frame;
and the image defect detection unit is used for guiding the current image frame and the previous image frame into a preset defect detector to obtain an image defect detection result, and determining whether the current image frame is an image to be repaired based on the image defect detection result.
Further, the image defect detecting unit specifically includes:
the first similarity calculation subunit is used for calculating the similarity between the current image frame and the previous image frame to obtain a first similarity;
the first similarity comparison subunit is used for comparing the first similarity with a preset similarity threshold value;
and the first similarity comparison result subunit is used for determining the current image frame as the image to be restored when the first similarity is smaller than a preset similarity threshold value.
Further, the deformation matrix optimization module 304 specifically includes:
the matrix normalization unit is used for performing normalization processing on the deformation matrix to obtain an initial fusion weight matrix;
the weight factor calculation unit is used for calculating the weight factor of the image to be restored and constructing a deformation matrix optimization function based on the weight factor;
the function iteration unit is used for iterating the deformation matrix optimization function based on a Newton method;
and the deformation matrix optimization unit is used for optimizing the initial fusion weight matrix through the iterated deformation matrix optimization function to obtain a fusion weight matrix.
Further, the image defect detecting unit further includes:
the second similarity calculation operator unit is used for guiding the obtained repaired image frame and the previous image frame into a preset defect detector, and calculating the similarity between the repaired image frame and the previous image frame to obtain a second similarity;
the second similarity comparison subunit is used for comparing the second similarity with a preset similarity threshold value;
and the second similarity comparison result subunit is used for continuously carrying out image restoration on the restored image frame when the second similarity is smaller than the preset similarity threshold value until the second similarity is larger than or equal to the preset similarity threshold value.
The application discloses device of blurred image correction belongs to artificial intelligence technical field. Because the image frames in the target video are often continuous, although the quality of the extracted target image frame is not excellent, the information contained in the fuzzy part of the target image is deduced from the image at the moment of the target image frame, and the information is fused with the target image, so that the information of the image can be recovered, and the aim of image restoration is fulfilled. According to the method, the image to be restored is determined in all image frames of the target video through a preset image detection strategy, the image to be restored is led into a pre-trained image deformation prediction model to obtain a deformation matrix of the image to be restored, a deformation matrix optimization function is constructed, the deformation matrix is subjected to iterative updating based on the deformation matrix optimization function to obtain an image fusion weight matrix, the image to be restored and the image of the previous frame of the image to be restored are subjected to image fusion based on the image fusion weight matrix to obtain a restored image, and the restored image is replaced by the obtained restored image. The technical scheme of the application can correct the image blur caused by high-speed movement or low-speed movement of the object, has high adaptability, does not increase the occupation of system resources, does not increase the overhead of the system, and is suitable for being deployed at the mobile terminal.
In order to solve the technical problem, an embodiment of the present application further provides a computer device. Referring to fig. 4, fig. 4 is a block diagram of a basic structure of a computer device according to the present embodiment.
The computer device 4 comprises a memory 41, a processor 42, a network interface 43 communicatively connected to each other via a system bus. It is noted that only computer device 4 having components 41-43 is shown, but it is understood that not all of the shown components are required to be implemented, and that more or fewer components may be implemented instead. As will be understood by those skilled in the art, the computer device is a device capable of automatically performing numerical calculation and/or information processing according to a preset or stored instruction, and the hardware includes, but is not limited to, a microprocessor, an Application Specific Integrated Circuit (ASIC), a Programmable Gate Array (FPGA), a Digital Signal Processor (DSP), an embedded device, and the like.
The computer device can be a desktop computer, a notebook, a palm computer, a cloud server and other computing devices. The computer equipment can carry out man-machine interaction with a user through a keyboard, a mouse, a remote controller, a touch panel or voice control equipment and the like.
The memory 41 includes at least one type of readable storage medium including a flash memory, a hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a Programmable Read Only Memory (PROM), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the memory 41 may be an internal storage unit of the computer device 4, such as a hard disk or a memory of the computer device 4. In other embodiments, the memory 41 may also be an external storage device of the computer device 4, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the computer device 4. Of course, the memory 41 may also include both internal and external storage devices of the computer device 4. In this embodiment, the memory 41 is generally used for storing an operating system installed in the computer device 4 and various types of application software, such as computer readable instructions of a method for correcting a blurred image. Further, the memory 41 may also be used to temporarily store various types of data that have been output or are to be output.
The processor 42 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data Processing chip in some embodiments. The processor 42 is typically used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is configured to execute computer readable instructions stored in the memory 41 or to process data, such as computer readable instructions for executing the method of blur image correction.
The network interface 43 may comprise a wireless network interface or a wired network interface, and the network interface 43 is generally used for establishing communication connection between the computer device 4 and other electronic devices.
The application discloses computer equipment belongs to artificial intelligence technical field. Because the image frames in the target video are often continuous, although the quality of the extracted target image frame is not excellent, the information contained in the fuzzy part of the target image is deduced from the image at the moment of the target image frame, and the information is fused with the target image, so that the information of the image can be recovered, and the aim of image restoration is fulfilled. According to the method, the image to be restored is determined in all image frames of the target video through a preset image detection strategy, the image to be restored is led into a pre-trained image deformation prediction model to obtain a deformation matrix of the image to be restored, a deformation matrix optimization function is constructed, the deformation matrix is subjected to iterative updating based on the deformation matrix optimization function to obtain an image fusion weight matrix, the image to be restored and the image of the previous frame of the image to be restored are subjected to image fusion based on the image fusion weight matrix to obtain a restored image, and the restored image is replaced by the obtained restored image. The technical scheme of the application can correct the image blur caused by high-speed movement or low-speed movement of the object, has high adaptability, does not increase the occupation of system resources, does not increase the overhead of the system, and is suitable for being deployed at the mobile terminal.
The present application further provides another embodiment, which is to provide a computer-readable storage medium storing computer-readable instructions executable by at least one processor to cause the at least one processor to perform the steps of the method of blurred image correction as described above.
The application discloses a storage medium belongs to artificial intelligence technical field. Because the image frames in the target video are often continuous, although the quality of the extracted target image frame is not excellent, the information contained in the fuzzy part of the target image is deduced from the image at the moment of the target image frame, and the information is fused with the target image, so that the information of the image can be recovered, and the aim of image restoration is fulfilled. According to the method, the image to be restored is determined in all image frames of the target video through a preset image detection strategy, the image to be restored is led into a pre-trained image deformation prediction model to obtain a deformation matrix of the image to be restored, a deformation matrix optimization function is constructed, the deformation matrix is subjected to iterative updating based on the deformation matrix optimization function to obtain an image fusion weight matrix, the image to be restored and the image of the previous frame of the image to be restored are subjected to image fusion based on the image fusion weight matrix to obtain a restored image, and the restored image is replaced by the obtained restored image. The technical scheme of the application can correct the image blur caused by high-speed movement or low-speed movement of the object, has high adaptability, does not increase the occupation of system resources, does not increase the overhead of the system, and is suitable for being deployed at the mobile terminal.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present application.
It is to be understood that the above-described embodiments are merely illustrative of some, but not restrictive, of the broad invention, and that the appended drawings illustrate preferred embodiments of the invention and do not limit the scope of the invention. This application is capable of embodiments in many different forms and is provided for the purpose of enabling a thorough understanding of the disclosure of the application. Although the present application has been described in detail with reference to the foregoing embodiments, it will be apparent to one skilled in the art that the present application may be practiced without modification or with equivalents of some of the features described in the foregoing embodiments. All equivalent structures made by using the contents of the specification and the drawings of the present application are directly or indirectly applied to other related technical fields and are within the protection scope of the present application.
Claims (10)
1. A method of blurred image correction, comprising:
receiving an image restoration instruction, acquiring a target video corresponding to the image restoration instruction, and acquiring all image frames in the target video;
determining an image to be restored in all image frames of the target video based on a preset image detection strategy;
importing the detected image to be restored into a pre-trained image deformation prediction model to obtain a deformation matrix of the image to be restored;
constructing a deformation matrix optimization function, and performing iterative update on the deformation matrix based on the deformation matrix optimization function to obtain an image fusion weight matrix;
and carrying out image fusion on the image to be repaired and the image of the previous frame of the image to be repaired based on the image fusion weight matrix to obtain a repaired image, and replacing the image to be repaired by the repaired image.
2. The method for blurred image correction according to claim 1, further comprising, after the steps of receiving an image restoration instruction, acquiring a target video corresponding to the image restoration instruction, and acquiring all image frames in the target video:
carrying out graying processing on all the image frames respectively to obtain a grayscale image of each image frame;
and carrying out normalization processing on the gray level image of each image frame to obtain a normalized image matrix corresponding to each image frame.
3. The method for blurred image correction according to claim 1, wherein the step of determining the image to be restored in all image frames of the target video based on the preset image detection strategy further comprises:
detecting a first image frame of the target video based on a preset standard image index, and judging whether the first image frame is a standard image frame;
if the first image frame is not the standard image frame, the target video corresponding to the image restoration instruction is intercepted again.
4. The method for blurred image correction according to claim 3, wherein the step of determining the image to be restored in all image frames of the target video based on the preset image detection strategy specifically comprises:
acquiring two image frames connected in time sequence from the target video, wherein the two image frames connected in time sequence are a current image frame and a previous image frame at a previous moment of the current image frame;
and importing the current image frame and the previous image frame into a preset defect detector to obtain an image defect detection result, and determining whether the current image frame is an image to be repaired based on the image defect detection result.
5. The method for correcting blurred images as claimed in claim 4, wherein the step of guiding the current image frame and the previous image frame to a preset defect detector to obtain an image defect detection result, and determining whether the current image frame is an image to be repaired based on the image defect detection result specifically comprises:
calculating the similarity between the current image frame and the previous image frame to obtain a first similarity;
comparing the first similarity with a preset similarity threshold;
and if the first similarity is smaller than a preset similarity threshold, determining that the current image frame is an image to be restored.
6. The method for correcting the blurred image according to any one of claims 1 to 5, wherein the step of constructing a deformation matrix optimization function, and iteratively updating the deformation matrix based on the deformation matrix optimization function to obtain an image fusion weight matrix specifically comprises:
carrying out normalization processing on the deformation matrix to obtain an initial fusion weight matrix;
calculating a weight factor of the image to be restored, and constructing the deformation matrix optimization function based on the weight factor;
iterating the deformation matrix optimization function based on a Newton method;
and optimizing the initial fusion weight matrix through the iterated deformation matrix optimization function to obtain a fusion weight matrix.
7. The method for blurred image correction according to claim 5, wherein after the image fusion is performed on the image to be repaired and the image in the previous frame of the image to be repaired based on the image fusion weight matrix to obtain a repaired image, and the image to be repaired is replaced by the repaired image, the method further comprises:
leading the obtained repaired image frame and the previous image frame into a preset defect detector, and calculating the similarity between the repaired image frame and the previous image frame to obtain a second similarity;
comparing the second similarity with a preset similarity threshold;
and if the second similarity is smaller than a preset similarity threshold, continuously repairing the image of the repaired image frame until the second similarity is larger than or equal to the preset similarity threshold.
8. An apparatus for blurred image correction, comprising:
the target video acquisition module is used for receiving an image restoration instruction, acquiring a target video corresponding to the image restoration instruction and acquiring all image frames in the target video;
the to-be-repaired image determining module is used for determining an image to be repaired in all image frames of the target video based on a preset image detection strategy;
the deformation matrix obtaining module is used for importing the detected image to be repaired into a pre-trained image deformation prediction model to obtain a deformation matrix of the image to be repaired;
the deformation matrix optimization module is used for constructing a deformation matrix optimization function, and iteratively updating the deformation matrix based on the deformation matrix optimization function to obtain an image fusion weight matrix;
and the image restoration module is used for carrying out image fusion on the image to be restored and the image of the previous frame of the image to be restored based on the image fusion weight matrix to obtain a restored image, and replacing the image to be restored by the restored image.
9. A computer device comprising a memory having computer readable instructions stored therein and a processor which when executed implements the steps of the method of blurred image correction according to any of claims 1 to 7.
10. A computer-readable storage medium, having computer-readable instructions stored thereon, which, when executed by a processor, implement the steps of the method of blurred image correction according to any of claims 1 to 7.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011609062.4A CN112634170B (en) | 2020-12-30 | 2020-12-30 | Method, device, computer equipment and storage medium for correcting blurred image |
PCT/CN2021/090420 WO2022142009A1 (en) | 2020-12-30 | 2021-04-28 | Blurred image correction method and apparatus, computer device, and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011609062.4A CN112634170B (en) | 2020-12-30 | 2020-12-30 | Method, device, computer equipment and storage medium for correcting blurred image |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112634170A true CN112634170A (en) | 2021-04-09 |
CN112634170B CN112634170B (en) | 2023-11-21 |
Family
ID=75286638
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011609062.4A Active CN112634170B (en) | 2020-12-30 | 2020-12-30 | Method, device, computer equipment and storage medium for correcting blurred image |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN112634170B (en) |
WO (1) | WO2022142009A1 (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114283091A (en) * | 2021-12-27 | 2022-04-05 | 张世强 | Power equipment image recovery system based on video fusion |
WO2022142009A1 (en) * | 2020-12-30 | 2022-07-07 | 平安科技(深圳)有限公司 | Blurred image correction method and apparatus, computer device, and storage medium |
CN114913468A (en) * | 2022-06-16 | 2022-08-16 | 阿里巴巴(中国)有限公司 | Object repairing method, repair evaluating method, electronic device, and storage medium |
CN115100209A (en) * | 2022-08-28 | 2022-09-23 | 电子科技大学 | Camera-based image quality correction method and system |
WO2023279890A1 (en) * | 2021-07-06 | 2023-01-12 | 北京锐安科技有限公司 | Image processing method and apparatus, electronic device, and storage medium |
CN115760609A (en) * | 2022-11-14 | 2023-03-07 | 王育新 | Image optimization method and system |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116069646B (en) * | 2023-02-10 | 2023-08-11 | 中国人民解放军海军航空大学 | Test set determination method and system for multi-objective testability optimization |
CN115829524B (en) * | 2023-02-15 | 2023-05-09 | 山东铁路投资控股集团有限公司 | Remote auditing method, device and equipment for hidden engineering and readable storage medium |
CN117891225B (en) * | 2024-03-15 | 2024-06-04 | 深圳市元景工艺品有限公司 | Intelligent control method and system for metal badge ornament processing equipment |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6583823B1 (en) * | 1997-08-01 | 2003-06-24 | Sony Corporation | Methods, apparatuses, and mediums for repairing a pixel associated with motion-picture processes |
KR20110108929A (en) * | 2010-03-30 | 2011-10-06 | 중앙대학교 산학협력단 | Apparatus and method for color distortion correction of image by estimate of correction matrix |
CN103595980A (en) * | 2013-10-25 | 2014-02-19 | 西安电子科技大学 | Method for demosaicing color filtering array image based on outline non-local mean value |
CN108921898A (en) * | 2018-06-28 | 2018-11-30 | 北京旷视科技有限公司 | Pose of camera determines method, apparatus, electronic equipment and computer-readable medium |
CN111415319A (en) * | 2020-03-20 | 2020-07-14 | 成科扬 | Video image restoration method based on time sequence network prediction and pyramid fusion |
CN111553864A (en) * | 2020-04-30 | 2020-08-18 | 深圳市商汤科技有限公司 | Image restoration method and device, electronic equipment and storage medium |
WO2020231016A1 (en) * | 2019-05-16 | 2020-11-19 | Samsung Electronics Co., Ltd. | Image optimization method, apparatus, device and storage medium |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101976429B (en) * | 2010-10-27 | 2012-11-14 | 南京大学 | Cruise image based imaging method of water-surface aerial view |
CN103279939B (en) * | 2013-04-27 | 2016-01-20 | 北京工业大学 | A kind of image mosaic disposal system |
US10796480B2 (en) * | 2015-08-14 | 2020-10-06 | Metail Limited | Methods of generating personalized 3D head models or 3D body models |
CN109670503A (en) * | 2018-12-19 | 2019-04-23 | 北京旷视科技有限公司 | Label detection method, apparatus and electronic system |
CN112634170B (en) * | 2020-12-30 | 2023-11-21 | 平安科技(深圳)有限公司 | Method, device, computer equipment and storage medium for correcting blurred image |
-
2020
- 2020-12-30 CN CN202011609062.4A patent/CN112634170B/en active Active
-
2021
- 2021-04-28 WO PCT/CN2021/090420 patent/WO2022142009A1/en active Application Filing
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6583823B1 (en) * | 1997-08-01 | 2003-06-24 | Sony Corporation | Methods, apparatuses, and mediums for repairing a pixel associated with motion-picture processes |
KR20110108929A (en) * | 2010-03-30 | 2011-10-06 | 중앙대학교 산학협력단 | Apparatus and method for color distortion correction of image by estimate of correction matrix |
CN103595980A (en) * | 2013-10-25 | 2014-02-19 | 西安电子科技大学 | Method for demosaicing color filtering array image based on outline non-local mean value |
CN108921898A (en) * | 2018-06-28 | 2018-11-30 | 北京旷视科技有限公司 | Pose of camera determines method, apparatus, electronic equipment and computer-readable medium |
WO2020231016A1 (en) * | 2019-05-16 | 2020-11-19 | Samsung Electronics Co., Ltd. | Image optimization method, apparatus, device and storage medium |
CN111415319A (en) * | 2020-03-20 | 2020-07-14 | 成科扬 | Video image restoration method based on time sequence network prediction and pyramid fusion |
CN111553864A (en) * | 2020-04-30 | 2020-08-18 | 深圳市商汤科技有限公司 | Image restoration method and device, electronic equipment and storage medium |
Non-Patent Citations (1)
Title |
---|
陈清江 等: "一种基于深度学习的多聚焦图像融合算法", 激光与光电子学进展, vol. 55, no. 07, pages 240 - 248 * |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2022142009A1 (en) * | 2020-12-30 | 2022-07-07 | 平安科技(深圳)有限公司 | Blurred image correction method and apparatus, computer device, and storage medium |
WO2023279890A1 (en) * | 2021-07-06 | 2023-01-12 | 北京锐安科技有限公司 | Image processing method and apparatus, electronic device, and storage medium |
CN114283091A (en) * | 2021-12-27 | 2022-04-05 | 张世强 | Power equipment image recovery system based on video fusion |
CN114283091B (en) * | 2021-12-27 | 2022-08-09 | 国网黑龙江省电力有限公司伊春供电公司 | Power equipment image recovery system based on video fusion |
CN114913468A (en) * | 2022-06-16 | 2022-08-16 | 阿里巴巴(中国)有限公司 | Object repairing method, repair evaluating method, electronic device, and storage medium |
CN115100209A (en) * | 2022-08-28 | 2022-09-23 | 电子科技大学 | Camera-based image quality correction method and system |
CN115100209B (en) * | 2022-08-28 | 2022-11-08 | 电子科技大学 | Camera-based image quality correction method and correction system |
CN115760609A (en) * | 2022-11-14 | 2023-03-07 | 王育新 | Image optimization method and system |
Also Published As
Publication number | Publication date |
---|---|
CN112634170B (en) | 2023-11-21 |
WO2022142009A1 (en) | 2022-07-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112634170B (en) | Method, device, computer equipment and storage medium for correcting blurred image | |
CN111709339B (en) | Bill image recognition method, device, equipment and storage medium | |
CN112052787B (en) | Target detection method and device based on artificial intelligence and electronic equipment | |
WO2022105125A1 (en) | Image segmentation method and apparatus, computer device, and storage medium | |
CN111311485B (en) | Image processing method and related device | |
CN112101520A (en) | Risk assessment model training method, business risk assessment method and other equipment | |
WO2023035531A1 (en) | Super-resolution reconstruction method for text image and related device thereof | |
CN112528029A (en) | Text classification model processing method and device, computer equipment and storage medium | |
CN112418292A (en) | Image quality evaluation method and device, computer equipment and storage medium | |
CN114882321A (en) | Deep learning model training method, target object detection method and device | |
CN114663952A (en) | Object classification method, deep learning model training method, device and equipment | |
CN111767750A (en) | Image processing method and device | |
EP4343616A1 (en) | Image classification method, model training method, device, storage medium, and computer program | |
CN114550051A (en) | Vehicle loss detection method and device, computer equipment and storage medium | |
CN112990583A (en) | Method and equipment for determining mold entering characteristics of data prediction model | |
CN112651399B (en) | Method for detecting same-line characters in inclined image and related equipment thereof | |
CN112633200A (en) | Human face image comparison method, device, equipment and medium based on artificial intelligence | |
CN112434746A (en) | Pre-labeling method based on hierarchical transfer learning and related equipment thereof | |
CN114241411A (en) | Counting model processing method and device based on target detection and computer equipment | |
CN113362249A (en) | Text image synthesis method and device, computer equipment and storage medium | |
CN113762027B (en) | Abnormal behavior identification method, device, equipment and storage medium | |
CN111798376B (en) | Image recognition method, device, electronic equipment and storage medium | |
WO2022178975A1 (en) | Noise field-based image noise reduction method and apparatus, device, and storage medium | |
CN113869317A (en) | License plate recognition method and device, electronic equipment and storage medium | |
CN114049646A (en) | Bank card identification method and device, computer equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |